click here to download the abstract project
ABSTRACT
The idea presented on this paper is proposed for an application of the ocr. The main purpose of this project is to recognize the printed text character from any natural image which contains text and do spelling corrections and generate text file and convert it into speech signal. Along with this the application should also provide special features like spell correction and voice selection options dictionary and image to text output saving capabilities. In this project Image text recognition and converting to speech involves several steps. First we have to preprocess the input image like converting the image into grayscale image and adding some threshold values to make text recognition easier. Then the preprocessed image is given as input to an OCR module to extract text from the image. The recognized text is given to name detection algorithm, here the native words are collected and text is thereby given to the spell correction algorithm ,then spell checking will be done after this algorithm, and then the native words are replaced with previous collected words and the corrected words will be given as input to the TTS module to get the final output. Based on these features the author predicts that the application gives more accuracy and the accuracy is 96 .21%
Key words: OCR, TTS, Name Detection, Symspell Correction.
INTRODUCTION
Digital Image Processing means processing digital images by means of a digital computer. We can also say that it is a use of computer algorithms, in order to get enhanced images to extract some useful information. Digital image processing deals with manipulation of digital images through a digital computer. It is a subfield of signals and systems but focuses particularly on images. DIP focuses on developing a computer system that is able to perform processing on an image. The input of that system is a digital image and the system processes that image using efficient algorithms, and gives an image as an output.
Image processing mainly include the following steps:
- Importing the image via image acquisition tools.
- Analyzing and manipulating the image.
- Output in which the result can be altered or a report which is based on analyzing that image.
Advantages: - Remove noises.
- Correct image density and contrast.
- Helps to easily store and retrieve in computers.
- Images can be made available in any desired formats like black and white, negative
images.
Disadvantages: - Initial cost is high depending upon the system used.
- Once the system is damaged the image will be lost.
